Visualizing and Understanding Deep Neural Networks in CTR Prediction
This work addresses the problem of model interpretability for practitioners in online advertising, but it is incremental as it applies existing visualization techniques to a new domain.
The paper tackles the challenge of interpreting deep neural networks in CTR prediction by visualizing inner neuron status, measuring layer-wise performance, and calculating input feature saliency scores, with experiments conducted on productive online advertising data.
Although deep learning techniques have been successfully applied to many tasks, interpreting deep neural network models is still a big challenge to us. Recently, many works have been done on visualizing and analyzing the mechanism of deep neural networks in the areas of image processing and natural language processing. In this paper, we present our approaches to visualize and understand deep neural networks for a very important commercial task--CTR (Click-through rate) prediction. We conduct experiments on the productive data from our online advertising system with daily varying distribution. To understand the mechanism and the performance of the model, we inspect the model's inner status at neuron level. Also, a probe approach is implemented to measure the layer-wise performance of the model. Moreover, to measure the influence from the input features, we calculate saliency scores based on the back-propagated gradients. Practical applications are also discussed, for example, in understanding, monitoring, diagnosing and refining models and algorithms.